Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OpenAEC-Foundation/OpenAEC-Workspace-Composer --skill tauri-agents-reviewgit clone --depth 1 https://github.com/OpenAEC-Foundation/OpenAEC-Workspace-ComposerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/openaec-foundation/openaec-workspace-composer/tauri-agents-review)<a href="https://agentmods.dev/skills/openaec-foundation/openaec-workspace-composer/tauri-agents-review"><img src="https://agentmods.dev/badge/skills/openaec-foundation/openaec-workspace-composer/tauri-agents-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/openaec-foundation/openaec-workspace-composer/tauri-agents-review"><img src="https://agentmods.dev/badge/skills/openaec-foundation/openaec-workspace-composer/tauri-agents-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.02839 |
| Opus 5.5 | $0.00037 | $0.01136 |
| Sonnet 5.5 | $0.00019 | $0.00568 |
| Haiku 4.5 | $0.00009 | $0.00284 |
Grade A, and why
tauri-agents-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tauri-agents-review
Review Workflow
Execute these checklists in order. Each section is independent -- report all findings, do not stop at the first issue.
Review Order:
1. Commands & IPC Bridge --> Rust signatures + JS invoke pairing
2. Permissions & Capabilities --> ACL coverage
3. State Management --> Thread safety + correctness
4. Error Handling --> Result types + frontend catching
5. Security --> CSP + scopes + dangerous settings
6. Build Configuration --> Config completeness
7. Anti-Pattern Scan --> Known mistakes
Checklist 1: Commands & IPC Bridge
1A: Rust Command Signatures
For every #[tauri::command] function, verify:
[ ] NEVER mark commands as pub if defined directly in lib.rs
[ ] ALWAYS mark commands as pub if defined in a separate module
[ ] ALWAYS use owned types (String, not &str) for async command parameters
Exception: &str allowed if return type is Result<T, E>
[ ] ALWAYS return Result<T, E> for any fallible operation
[ ] ALWAYS implement serde::Serialize on the error type E
[ ] ALWAYS implement serde::Deserialize on all custom parameter types
[ ] ALWAYS implement serde::Serialize on all custom return value types
[ ] ALWAYS implement both Serialize AND Clone on event payload types
1B: Command Registration
[ ] ALWAYS list all commands in a SINGLE generate_handler![] call
NEVER use multiple .invoke_handler() calls on Builder
[ ] ALWAYS register every #[tauri::command] function
Cross-reference: grep for #[tauri::command] and compare with generate_handler![]
[ ] ALWAYS use correct module paths (e.g., commands::greet, not just greet)
1C: IPC Bridge Completeness
For every Rust command, verify a matching frontend invoke exists:
[ ] ALWAYS verify invoke('command_name', ...) call exists in TypeScript/JavaScript
[ ] ALWAYS use camelCase argument keys (NEVER use snake_case in frontend invoke calls)
[ ] ALWAYS match argument types to Rust parameter types:
- Rust String <-> JS string
- Rust i32/u32/u64/f64 <-> JS number
- Rust bool <-> JS boolean
- Rust Vec<T> <-> JS array
- Rust Option<T> <-> JS null/undefined
[ ] ALWAYS specify return type generic: invoke<ExpectedType>('...')
[ ] ALWAYS handle error case with try/catch
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 389 lines · 93 tokens per session scan A 59c8fdd988af
tauri-agents-review is a skill published in the GitHub repository OpenAEC-Foundation/OpenAEC-Workspace-Composer (6 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 2,839 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
tauri-agents-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tauri-agents-reviewOpenAEC-Foundation/OpenAEC-Workspace-Composer | Skill | 6 | 1mo ago | MIT | A | 93 | Claude Code |
| aios-reviewArchSightLabs/archsight-aios | Skill | 29 | 1mo ago | Apache-2.0 | A | 55 | Claude Code, Codex |
| receiving-code-reviewandrooAGI/starnet | Skill | 1.7k | 6d ago | MIT | A | 48 | Claude Code, Codex |
| ha-code-reviewshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 40 | Claude Code |
| address-pr-commentsandrooAGI/starnet | Skill | 1.7k | 6d ago | MIT | A | 46 | Claude Code, Codex |
| dsh-code-reviewqufei1993/skills-hub | Skill | 1.9k | 5d ago | MIT | A | 46 | Codex |
| dsh-find-simplificationsqufei1993/skills-hub | Skill | 1.9k | 5d ago | MIT | A | 42 | Codex |